PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition
This work addresses the need for more effective data augmentation in speech recognition, offering an incremental improvement by complementing existing amplitude-based methods.
The paper tackles the problem of limited speech data diversity in automatic speech recognition by proposing PhasePerturbation, a novel data augmentation method that dynamically perturbs the phase spectrum of speech, resulting in a 10.9% relative reduction in word error rate on the TIMIT corpus.
Most of the current speech data augmentation methods operate on either the raw waveform or the amplitude spectrum of speech. In this paper, we propose a novel speech data augmentation method called PhasePerturbation that operates dynamically on the phase spectrum of speech. Instead of statically rotating a phase by a constant degree, PhasePerturbation utilizes three dynamic phase spectrum operations, i.e., a randomization operation, a frequency masking operation, and a temporal masking operation, to enhance the diversity of speech data. We conduct experiments on wav2vec2.0 pre-trained ASR models by fine-tuning them with the PhasePerturbation augmented TIMIT corpus. The experimental results demonstrate 10.9\% relative reduction in the word error rate (WER) compared with the baseline model fine-tuned without any augmentation operation. Furthermore, the proposed method achieves additional improvements (12.9\% and 15.9\%) in WER by complementing the Vocal Tract Length Perturbation (VTLP) and the SpecAug, which are both amplitude spectrum-based augmentation methods. The results highlight the capability of PhasePerturbation to improve the current amplitude spectrum-based augmentation methods.